© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 118972
    Prev
    Next
    INDEX
    Explanations

    casserole dishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    सामान्यीकृत
    0.58
    毉
    0.57
     fennel
    0.55
     제외
    0.53
     oncology
    0.52
     относя
    0.52
    ioides
    0.52
     ограни
    0.51
     মাথ
    0.51
     perfusion
    0.51
    POSITIVE LOGITS
    e
    0.60
     ដ
    0.60
    popular
    0.59
    SP
    0.58
    0
    0.54
    highly
    0.53
    hoti
    0.53
     juz
    0.53
     zir
    0.53
    IMAGES
    0.52
    Activations Density 0.001%

    No Known Activations